LSTM Two Input one outpot in Matlab Example

In Matlab's LSTM Example of sequence-to-sequence regression, there was one input vector (number of cases) and one output (prediction of the number of cases) in the regression.

How in this example I can added two additional vectors and one output (prediction of the number of cases) so the two additiona features will reduce the RMSE?

Thank you

Answer 1

[Marcelo Olmedo]

Hello! The key is in the data entry. I leave you an example importing training data of 5 input variables and one output. Then the test is done and finally it is graphed. The example is very basic but it will give you a good idea of ​​the procedure

[Mohamed Nedal]

Hi @Marcelo,

I tried to add a few lines of code to predict new future values of the target output, here's what I added:

%% Forecast the Future 
net = resetState(net); 
Yforecast = []; 
numTimeStepsTest = numel(XTest) + 500;     % to forecast new 500 steps in the future 
for i = 1:numTimeStepsTest 
    [net, Yforecast(:,i)] = predictAndUpdateState(net, XTest(:,i), 'ExecutionEnvironment','cpu'); 
end 

but I got this error:

Conversion to double from cell is not possible.
Error in LSTM_multi_motores (line 82)
    [net, Yforecast(:,i)] = predictAndUpdateState(net, XTest(:,i),
    'ExecutionEnvironment','cpu'); 

Can you please tell me how to fix this part?

[Tasarruf Bashir]

hi@Marcelo Olmedo, i have tried your program with my dataset, having 6 inputs and one output, the rmse value without normalization is very high. but after the normalization the rmse value was dcreased from 1400 to 824. now i am trying to use the technique used in chickenpox example, but couldn't be able to figure out how to use it with multiple variables? can guide me in this regard? thanks in advance